SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.12246 · 2024

RT-OVAD: Real-Time Open-Vocabulary Aerial Object Detection via Image-Text Collaboration

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 4 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2408.12246.json · badge: /api/ran/2408.12246.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
GT-Wei/RT-OVAD canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
FunctionStatusWhere it lives
bias_init_with_prob Ran
ran, honoured the contract we drafted
GT-Wei/RT-OVAD/src/zoo/itc_ovad/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from shihuahuang95/deim, is pointer only (licence: NOASSERTION) · get_code("8c4a2df028bbf447")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shihuahuang95/deim, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

box_cxcywh_to_xyxy Ran
ran, honoured the contract we drafted
GT-Wei/RT-OVAD/src/zoo/itc_ovad/box_ops.py
code served (permissive licence) · get_code("e0a06ded5d4f6c3c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects a tensor x with shape (..., 4) where the last dimension
# contains [center_x, center_y, width, height] values
# It unbinds the last dimension and converts to [x_min, y_min, x_max, y_max]

x = torch.tensor([
    [10.0, 20.0, 4.0, 6.0],
    [30.0, 40.0, 8.0, 10.0]
])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
box_iou Ran
ran, honoured the contract we drafted
GT-Wei/RT-OVAD/src/zoo/itc_ovad/box_ops.py
code served (permissive licence) · get_code("ce749f837424dd8c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torchvision.ops.boxes import box_area

torch.manual_seed(0)

# Create two sets of bounding boxes in format [x1, y1, x2, y2]
# boxes1: 2 boxes
# boxes2: 3 boxes
boxes1 = torch.tensor([
    [0.0, 0.0, 2.0, 2.0],
    [1.0, 1.0, 3.0, 3.0]
], dtype=torch.float32)

boxes2 = torch.tensor([
    [0.0, 0.0, 1.0, 1.0],
    [1.5, 1.5, 2.5, 2.5],
    [2.0, 2.0, 4.0, 4.0]
], dtype=torch.float32)

ARGS = {
    "boxes1": boxes1,
    "boxes2": boxes2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
box_xyxy_to_cxcywh Ran
ran, honoured the contract we drafted
GT-Wei/RT-OVAD/src/zoo/itc_ovad/box_ops.py
code served (permissive licence) · get_code("031b02fb990284ba")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects a tensor x with shape (..., 4) where the last dimension
# contains [x0, y0, x1, y1] coordinates (xyxy format)
# It unbinds the last dimension and converts to center-xy, width, height format

x = torch.tensor([
    [10.0, 20.0, 30.0, 40.0],
    [5.0, 15.0, 25.0, 35.0]
])

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
deformable_attention_core_func Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GT-Wei/RT-OVAD/src/zoo/itc_ovad/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from shihuahuang95/deim, is pointer only (licence: NOASSERTION) · get_code("9524bdc261cbc2dc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shihuahuang95/deim, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_schema Ran
ran on a synthesized input
GT-Wei/RT-OVAD/src/core/yaml_utils.py
code served (permissive licence) · get_code("719ffaab32332a71")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import inspect
import importlib
import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a test class to pass to extract_schema
class SimpleModel(nn.Module):
    def __init__(self, input_dim=10, hidden_dim=5, output_dim=2):
        super().__init__()
        self.linear = nn.Linear(input_dim, hidden_dim)
    
    __inject__ = ['input_dim']
    __share__ = ['hidden_dim']

# Another test class with required and optional arguments
class AnotherClass:
    def __init__(self, required_arg, optional_arg=42):
        self.required_arg = required_arg
        self.optional_arg = optional_arg

# Test class with no special attributes
class MinimalClass:
    def __init__(self, x, y=10):
        self.x = x
        self.y = y

ARGS = {
    'cls': SimpleModel
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
init_distributed Ran
ran, violated the contract we drafted
GT-Wei/RT-OVAD/src/misc/dist.py
code served (permissive licence) · get_code("f4c8d56689a4f3bb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.distributed as tdist
from datetime import timedelta
import os

# Set up environment variables for single-process distributed testing
# world_size=1 means distributed mode won't actually initialize
os.environ['WORLD_SIZE'] = '1'
os.environ['RANK'] = '0'
os.environ['LOCAL_RANK'] = '0'

ARGS = {
    'backend': 'nccl',
    'timeout_sec': 36000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
inverse_sigmoid Ran
ran; our contract draft was wrong, not the code
GT-Wei/RT-OVAD/src/zoo/itc_ovad/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from shihuahuang95/deim, is pointer only (licence: NOASSERTION) · get_code("2fff86fc7c917b0c")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from shihuahuang95/deim, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

register Ran
ran on a synthesized input
GT-Wei/RT-OVAD/src/core/yaml_utils.py
code served (permissive licence) · get_code("ac0b264881e880f3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned type. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import inspect
from typing import Callable

torch.manual_seed(0)

# Define a minimal test class to register
class SimpleModel:
    """A simple class with various argument types"""
    def __init__(self, input_dim: int, hidden_dim: int = 64, use_bias: bool = True):
        self.input_dim = input_dim
        self.hidden_dim = hidden_dim
        self.use_bias = use_bias
    
    __inject__ = []
    __share__ = []

class AnotherTestClass:
    """Another class for testing registration"""
    def __init__(self, name: str, value: float = 0.5):
        self.name = name
        self.value = value
    
    __inject__ = ['name']
    __share__ = ['value']

def test_function(x: int, y: str = "default"):
    """A test function to register"""
    return x + len(y)

GLOBAL_CONFIG = dict()

ARGS = {
    'cls': SimpleModel
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
warp_loader Ran
ran; our contract draft was wrong, not the code
GT-Wei/RT-OVAD/src/misc/dist.py
code served (permissive licence) · get_code("4a10ae76733a083c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned DataLoader. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from torch.utils.data import DataLoader, TensorDataset

torch.manual_seed(0)

# Create a minimal dataset
x = torch.randn(8, 4)
y = torch.randint(0, 2, (8,))
dataset = TensorDataset(x, y)

# Create a minimal DataLoader with all necessary attributes
loader = DataLoader(
    dataset=dataset,
    batch_size=2,
    shuffle=False,
    drop_last=False,
    collate_fn=None,
    pin_memory=False,
    num_workers=0
)

ARGS = {
    "loader": loader,
    "shuffle": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
warp_model Ran
ran; our contract draft was wrong, not the code
GT-Wei/RT-OVAD/src/misc/dist.py
code served (permissive licence) · get_code("fe4645cb6c103d24")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned SimpleModel. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import os

torch.manual_seed(0)

# Create a minimal model that warp_model can work with
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.bn = nn.BatchNorm1d(3)
    
    def forward(self, x):
        x = self.linear(x)
        x = self.bn(x)
        return x

model = SimpleModel()

ARGS = {
    'model': model,
    'find_unused_parameters': False,
    'sync_bn': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimpleModel — a SimpleModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create Not yet run
unverified (harvested, no recorded run)
GT-Wei/RT-OVAD/src/core/yaml_utils.py
code served (permissive licence) · get_code("da548fcd02ec18bd")
How it ran

no invocation recorded.

get_contrastive_denoising_training_group Not yet run
unverified (harvested, no recorded run)
GT-Wei/RT-OVAD/src/zoo/itc_ovad/denoising.py
code served (permissive licence) · get_code("676f3037319214be")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 10 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 10 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
box_cxcywh_to_xyxy 49 other papers
35 dated earlier, 3 the same month, 11 later · 11 only as an assembly brick
1811.07628 (2018-11)
ATOM: Accurate Tracking by Overlap Maximization
2011.10881 (2020-11)
Rethinking Transformer-based Set Prediction for Object Detection
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
and 46 more not named here
box_xyxy_to_cxcywh 45 other papers
30 dated earlier, 1 the same month, 14 later · 20 only as an assembly brick
2011.10881 (2020-11)
Rethinking Transformer-based Set Prediction for Object Detection
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
2103.17154 (2021-03)
Learning Spatio-Temporal Transformer for Visual Tracking
and 42 more not named here
box_iou 24 other papers
19 dated earlier, 4 later, 1 undated · 5 only as an assembly brick
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
2104.00969 (2021-04)
TubeR: Tubelet Transformer for Video Action Detection
2112.05375 (2021-12)
Rethinking the Two-Stage Framework for Grounded Situation Recognition
and 21 more not named here
bias_init_with_prob 1 other paper
1 later
2412.04234 (2024-12)
DEIM: DETR with Improved Matching for Fast Convergence
create 1 other paper
1 later
Wang_Object_Detection_using_Event_Camera_A_MoE_Heat_Conduction_based_CVPR_2025_paper (2025 (year only))
Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset
deformable_attention_core_func 1 other paper
1 later
2412.04234 (2024-12)
DEIM: DETR with Improved Matching for Fast Convergence
extract_schema 1 other paper
1 later
Wang_Object_Detection_using_Event_Camera_A_MoE_Heat_Conduction_based_CVPR_2025_paper (2025 (year only))
Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset
inverse_sigmoid 1 other paper
1 later
2412.04234 (2024-12)
DEIM: DETR with Improved Matching for Fast Convergence
register 1 other paper
1 later
Wang_Object_Detection_using_Event_Camera_A_MoE_Heat_Conduction_based_CVPR_2025_paper (2025 (year only))
Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset
warp_loader 1 other paper
1 later
Wang_Object_Detection_using_Event_Camera_A_MoE_Heat_Conduction_based_CVPR_2025_paper (2025 (year only))
Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Aerial object detection plays a crucial role in numerous applications. However, most existing methods focus on detecting predefined object categories, limiting their applicability in real-world open scenarios. In this paper, we extend aerial object detection to open scenarios through image-text collaboration and propose RT-OVAD, the first real-time open-vocabulary detector for aerial scenes. Specifically, we first introduce an image-to-text alignment loss to replace the conventional category regression loss, thereby eliminating category constraints. Next, we propose a lightweight image-text collaboration strategy comprising an image-text collaboration encoder and a text-guided decoder. The encoder simultaneously enhances visual features and refines textual embeddings, while the decoder guides object queries to focus on class-relevant image features. This design further improves detection accuracy without incurring significant computational overhead. Extensive experiments demonstrate that RT-OVAD consistently outperforms existing state-of-the-art methods across open-vocabulary, zero-shot, and traditional closed-set detection tasks. For instance, on the open-vocabulary aerial detection benchmarks DIOR, DOTA-v2.0, and LAE-80C, RT-OVAD achieves 87.7 AP$_{50}$, 53.8 mAP, and 23.7 mAP, respectively, surpassing the previous state-of-the-art (LAE-DINO) by 2.2, 7.0, and 3.5 points. In addition, RT-OVAD achieves an inference speed of 34 FPS on an RTX 4090 GPU, approximately three times faster than LAE-DINO (10 FPS), meeting the real-time detection requirements of diverse applications. The code will be released at https://github.com/GT-Wei/RT-OVAD.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.12246")
get_code_for_paper("2408.12246")
have("2408.12246")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.12246.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.12246.svg)](https://syntology.ai/paper/2408.12246)

Connect an agent — have() is free.